AI Paper Atlas

Research map / Point clouds / Registration and matching

PointCLM: A Contrastive Learning-Based Framework for Multi-Instance Point Cloud Registration

Mingzhi Yuan, Zhihao Li, Qiuye Jin, Xinrong Chen, Manning Wang

ECCV 2022 · Point clouds › Registration and matching · approach: Robust inlier selection for registration · 19 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add deep contrastive representation (ablation)PointCLM · Scan2CADMF (%): 70.36 -> 74.18Improved
add deep contrastive representation (ablation)PointCLM · Scan2CADTime (s): 0.17 -> 0.10Improved
add pruning (ablation)PointCLM · Scan2CADMF (%): 42.93 -> 74.18Improved
use hardest negative pairs instead of random (ablation)PointCLM · Scan2CADMF (%): 71.87 -> 74.18Improved
increase RANSAC iterations from 5 to 50 (ablation)PointCLM · Scan2CADMF (%): 72.26 -> 74.18Improved
increase RANSAC iterations from 50 to 500 (ablation)PointCLM · Scan2CADMF (%): 74.18 -> 74.73No clear effect
raise tau_S from 0.85 to 0.90 (ablation)PointCLM · Scan2CADMR (%): 78.10 -> 74.06Hurt
lower tau_S from 0.85 to 0.75 (ablation)PointCLM · Scan2CADMF (%): 74.18 -> 73.71No clear effect
lower tau_N from 20 to 10 (ablation)PointCLM · Scan2CADMP (%): 70.64 -> 61.44Hurt
lower tau_N from 20 to 10 (ablation)PointCLM · Scan2CADMR (%): 78.10 -> 80.60Improved
random negatives vs no deep representation (ablation)PointCLM · Scan2CADMF (%): 70.36 -> 71.87No clear effect

Later papers that compared with this method

1 later accepted paper reports PointCLM as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy